.png){kind=icon}
Return
Cross Knowledge-based Generative Zero-Shot Learning approach with Taxonomy Regularization
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2021.02.009.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Although zero-shot learning (ZSL) has an inferential capability of recognizing new classes that have never been seen before, it always faces two fundamental challenges of the cross modality and cross domain challenges. In order to alleviate these problems, we develop a generative network-based ZSL approach equipped with the proposed Cross Knowledge Learning (CKL) scheme and Taxonomy Regularization (TR). In our approach, the semantic features are taken as inputs, and the output is the synthesized visual features generated from the corresponding semantic features. CKL enables more relevant semantic features to be trained for semantic-to-visual feature embedding in ZSL, while Taxonomy Regularization (TR) significantly improves the intersections with unseen images with more generalized visual features generated from generative network. Extensive experiments on several benchmark datasets (i.e., AwA1, AwA2, CUB, NAB and aPY) show that our approach is superior to these state-of-the-art methods in terms of ZSL image classification and retrieval. (C) 2021 Elsevier Ltd. All rights reserved.
Keywords:
Zero-Shot Learning
Image recognition
Generative Adversarial Network
Knowledge engineering
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.3
Papers:
8.2K
Citations:
3.0W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSave
ShareSaveShareSave
View more